Comments (10)
@ryusaeba
The slight difference comes from the blas algorithm. I did not employ the blas lib, while the original conv layer did.
I assume the blas algorithm sacrifice slight precision to get better performance, because the depthwise outputs matches my handcraft computation.
from depthwiseconvolution.
He already implement the cpu version,you can find that in code.
from depthwiseconvolution.
But looks like cpu version does not optimized for depthwise conversion.
from depthwiseconvolution.
I'm sorry for uncertainty about this.
It's a tough work and I am right busy on other work.
from depthwiseconvolution.
Hi @yonghenglh6
Can we use your cpp/hpp/cu files to load MobileNet you pasted as pretrained weight to do finetune work? I have this question is because when we update conv to depthwsie, caffe still can load the pretrained weight? Or caffe base on layer {name} to load the pretrained weight?
from depthwiseconvolution.
I check the website http://caffe.berkeleyvision.org/gathered/examples/finetune_flickr_style.html and saw the following statement. "If we provide the weights argument to the caffe train command, the pretrained weights will be loaded into our model, matching layers by name."
Therefore, I assume your answer is correct. If I am wrong, please correct me. Thanks!
from depthwiseconvolution.
@ryusaeba Yes, that's why I use the original conv_param instead of new special param. You can just change the type without compatible price.
from depthwiseconvolution.
@yonghenglh6 Thanks! I have got all pass message by using check.py. Then I apply DepthWiseConvlution on https://github.com/shicai/MobileNet-Caffe inference path, the TOP-1 result (accuracy) is the same but I get slight difference on loss. I assume the loss will be the same. Do you have any idea about this?
from depthwiseconvolution.
hello ,do you implement the DepthwiseConvolutionLayer for CPU?
from depthwiseconvolution.
.....wait
from depthwiseconvolution.
Related Issues (20)
- Why slower than tensorflow HOT 1
- how to change the two super-parameters ?And, trian time HOT 11
- error == cudaSuccess (77 vs. 0 ) an illegal memory access was encountered HOT 4
- Did somesone train some models with this DepthwiseConvolution layer? HOT 6
- Dose the restriction 'only for stride1' still hold? HOT 2
- why your deploy not have batch_norm_param { use_global_stats: true}??? HOT 1
- is this implementation support cudnn? HOT 1
- which vison of caffe did you use? When I use it on my caffe ,it got wrong.
- windows caffe编译
- only for stride 1? HOT 1
- Movidius ncsdk not support this HOT 1
- Unknown layer type: DepthwiseConvolution
- Except for the speed, does it perform like the original caffe convolution? HOT 1
- About group in deploy.prototxt
- Caffe (Windows) - version, build, usage?
- 与convd的不同 HOT 6
- Which GPU did you run the test with?
- only for dalition 1?
- affter add the 3 piece into caffe file, when make caffe, crt1.o error happen, how to solve it?
- just a copy of conv HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from depthwiseconvolution.